Sciweavers

Share
COLT
1995
Springer

On the Learnability and Usage of Acyclic Probabilistic Finite Automata

11 years 10 months ago
On the Learnability and Usage of Acyclic Probabilistic Finite Automata
We propose and analyze a distribution learning algorithm for a subclass of Acyclic Probabilistic Finite Automata (APFA). This subclass is characterized by a certain distinguishability property of the automata’s states. Though hardness results are known for learning distributionsgeneratedbygeneral APFAs,weprove that our algorithm can indeed efficiently learn distributions generated by the subclass of APFAs we consider. In particular, we show that the KLdivergence between the distribution generated by the target source and the distribution generated by our hypothesis can be made small with high confidence in polynomial time. We present two applications of our algorithm. In the first, we show how to model cursively written letters. The resulting models are part of a complete cursive handwriting recognition system. In the second applicationwe demonstrate howAPFAs can be used to build multiple-pronunciation models for spoken words. We evaluate the APFA based pronunciation models on la...
Dana Ron, Yoram Singer, Naftali Tishby
Added 25 Aug 2010
Updated 25 Aug 2010
Type Conference
Year 1995
Where COLT
Authors Dana Ron, Yoram Singer, Naftali Tishby
Comments (0)
books